| From d8781da59fa5ac26895944d0471082c571f99223 Mon Sep 17 00:00:00 2001 |
| From: Jens Axboe <axboe@kernel.dk> |
| Date: Tue, 26 May 2020 09:38:31 -0600 |
| Subject: [PATCH] sched/fair: Don't NUMA balance for kthreads |
| |
| commit 18f855e574d9799a0e7489f8ae6fd8447d0dd74a upstream. |
| |
| Stefano reported a crash with using SQPOLL with io_uring: |
| |
| BUG: kernel NULL pointer dereference, address: 00000000000003b0 |
| CPU: 2 PID: 1307 Comm: io_uring-sq Not tainted 5.7.0-rc7 #11 |
| RIP: 0010:task_numa_work+0x4f/0x2c0 |
| Call Trace: |
| task_work_run+0x68/0xa0 |
| io_sq_thread+0x252/0x3d0 |
| kthread+0xf9/0x130 |
| ret_from_fork+0x35/0x40 |
| |
| which is task_numa_work() oopsing on current->mm being NULL. |
| |
| The task work is queued by task_tick_numa(), which checks if current->mm is |
| NULL at the time of the call. But this state isn't necessarily persistent, |
| if the kthread is using use_mm() to temporarily adopt the mm of a task. |
| |
| Change the task_tick_numa() check to exclude kernel threads in general, |
| as it doesn't make sense to attempt ot balance for kthreads anyway. |
| |
| Reported-by: Stefano Garzarella <sgarzare@redhat.com> |
| Signed-off-by: Jens Axboe <axboe@kernel.dk> |
| Signed-off-by: Ingo Molnar <mingo@kernel.org> |
| Acked-by: Peter Zijlstra <peterz@infradead.org> |
| Link: https://lore.kernel.org/r/865de121-8190-5d30-ece5-3b097dc74431@kernel.dk |
| Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com> |
| |
| diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c |
| index 95667bb3daca..9ca90fc24207 100644 |
| --- a/kernel/sched/fair.c |
| +++ b/kernel/sched/fair.c |
| @@ -2659,7 +2659,7 @@ static void task_tick_numa(struct rq *rq, struct task_struct *curr) |
| /* |
| * We don't care about NUMA placement if we don't have memory. |
| */ |
| - if (!curr->mm || (curr->flags & PF_EXITING) || work->next != work) |
| + if ((curr->flags & (PF_EXITING | PF_KTHREAD)) || work->next != work) |
| return; |
| |
| /* |
| -- |
| 2.27.0 |
| |
